Horror Movies and Simulation

December 9, 2024

Shirley Toribio

Diversity of Horror

Netflix Horror Movies

horror_df
  num         genre
1 125        Horror
2 110     Thrillers
3  38      Comedies
4  19 SciFi&Fantasy
5  12          Cult
6   2 Documentaties
7   2      Romantic

Netflix Horror Movies

Beta vs Normal Distribution

Function 1: PI Interval Calculation

CI <- function(data, coverage_prob){ 
  #Generates a normal prediction interval with an intended coverage probability of coverage_prob based on a vector of numeric data
  lower_zscore <- qnorm((1-coverage_prob)/2)
  upper_zscore <- qnorm(((1-coverage_prob)/2) + coverage_prob)
  avg <- mean(data)
  stan_d <- sd(data)
  lower_bound <- avg + lower_zscore*stan_d
  upper_bound <- avg + upper_zscore*stan_d
  return(data.frame(PI_percentage = coverage_prob, lower = lower_bound, upper = upper_bound))
}

Function 2: One simulation of beta-generated data

one_beta_simulation <- function(n, alpha, beta, ci_prop){
  #Assesses prediction accuracy and actual coverage probability of a normal prediction interval when used on a vector of numeric data of size n. The numeric data is generated from a beta distribution with parameters alpha and beta.
  
  cover_df <- CI(rbeta(n, alpha, beta), ci_prop)
  cover_prop <- pbeta(cover_df[1, "upper"], alpha, beta) - pbeta(cover_df[1, "lower"], alpha, beta)
  mean_in_interval <- .5 >= cover_df[1, "lower"] & .5 <= cover_df[1,"upper"]
  param_df <- data.frame(cover = cover_prop, alpha = rep(alpha, nrow(cover_df)), beta = rep(beta, nrow(cover_df)), mean_in_interval = mean_in_interval)
  df <- cbind(cover_df, param_df)
  return(df)
}

Function 3: Multiple Beta simulations

beta_sims_n <- function(n){
  #Iterates over a vector of possible alpha = beta values and applies one_beta_simulation to each possible value of alpha/beta. All simulations use data of sample size n.
  df1 <- map(parameters,\(param) one_beta_simulation(n, param, param, ci) ) %>%
  list_rbind()
  df2 <- data.frame(n = rep(n, nrow(df1)))
  df <- cbind(df2, df1)
  return(df)
}

Simulations

     n PI_percentage     lower     upper     cover alpha beta mean_in_interval
1  455          0.95 0.4518613 0.5493738 0.9449629   193  193             TRUE
2  370          0.95 0.4073973 0.5872232 0.9461831    57   57             TRUE
3   32          0.95 0.2988644 0.6482433 0.9203282    13   13             TRUE
4  452          0.95 0.4412301 0.5585745 0.9327327   121  121             TRUE
5  474          0.95 0.4474210 0.5559983 0.9541341   169  169             TRUE
6  381          0.95 0.4275185 0.5746540 0.9428899    83   83             TRUE
7  265          0.95 0.4457077 0.5515220 0.9484484   169  169             TRUE
8   92          0.95 0.4444017 0.5499518 0.9579876   187  187             TRUE
9   55          0.95 0.4454341 0.5509372 0.9636713   197  197             TRUE
10  56          0.95 0.4414381 0.5691853 0.9253503    99   99             TRUE

Results

FIN